1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
|
# -*- coding: utf-8 -*-
# Copyright 2019-2025 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://fuskator.com/"""
from .common import GalleryExtractor, Extractor, Message
from .. import text
import time
class FuskatorGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries on fuskator.com"""
category = "fuskator"
root = "https://fuskator.com"
pattern = r"(?:https?://)?fuskator\.com/(?:thumbs|expanded)/([^/?#]+)"
example = "https://fuskator.com/thumbs/ID/"
def __init__(self, match):
self.gallery_hash = match[1]
url = f"{self.root}/thumbs/{self.gallery_hash}/index.html"
GalleryExtractor.__init__(self, match, url)
def metadata(self, page):
headers = {
"Referer" : self.page_url,
"X-Requested-With": "XMLHttpRequest",
}
auth = self.request(
self.root + "/ajax/auth.aspx", method="POST", headers=headers,
).text
params = {
"X-Auth": auth,
"hash" : self.gallery_hash,
"_" : int(time.time()),
}
self.data = data = self.request_json(
self.root + "/ajax/gal.aspx", params=params, headers=headers)
title = text.extr(page, "<title>", "</title>").strip()
title, _, gallery_id = title.rpartition("#")
return {
"gallery_id" : text.parse_int(gallery_id),
"gallery_hash": self.gallery_hash,
"title" : text.unescape(title[:-15]),
"views" : data.get("hits"),
"score" : data.get("rating"),
"tags" : (data.get("tags") or "").split(","),
}
def images(self, page):
return [
("https:" + image["imageUrl"], image)
for image in self.data["images"]
]
class FuskatorSearchExtractor(Extractor):
"""Extractor for search results on fuskator.com"""
category = "fuskator"
subcategory = "search"
root = "https://fuskator.com"
pattern = r"(?:https?://)?fuskator\.com(/(?:search|page)/.+)"
example = "https://fuskator.com/search/TAG/"
def __init__(self, match):
Extractor.__init__(self, match)
self.path = match[1]
def items(self):
url = self.root + self.path
data = {"_extractor": FuskatorGalleryExtractor}
while True:
page = self.request(url).text
for path in text.extract_iter(
page, 'class="pic_pad"><a href="', '"'):
yield Message.Queue, self.root + path, data
pages = text.extr(page, 'class="pages"><span>', '>>><')
if not pages:
return
url = self.root + text.rextr(pages, 'href="', '"')
|
